Relational Sentence Embedding for Flexible Semantic Matching
This addresses the problem of flexible semantic matching for natural language processing applications, offering a novel approach beyond simple similarity-based embeddings.
The paper tackles the challenge of capturing diverse semantic relations between sentences, such as entailment and paraphrasing, by introducing Relational Sentence Embedding (RSE), which uses relation-wise translation to infer target sentences and outperforms state-of-the-art methods on 19 benchmark datasets.
We present Relational Sentence Embedding (RSE), a new paradigm to further discover the potential of sentence embeddings. Prior work mainly models the similarity between sentences based on their embedding distance. Because of the complex semantic meanings conveyed, sentence pairs can have various relation types, including but not limited to entailment, paraphrasing, and question-answer. It poses challenges to existing embedding methods to capture such relational information. We handle the problem by learning associated relational embeddings. Specifically, a relation-wise translation operation is applied to the source sentence to infer the corresponding target sentence with a pre-trained Siamese-based encoder. The fine-grained relational similarity scores can be computed from learned embeddings. We benchmark our method on 19 datasets covering a wide range of tasks, including semantic textual similarity, transfer, and domain-specific tasks. Experimental results show that our method is effective and flexible in modeling sentence relations and outperforms a series of state-of-the-art sentence embedding methods. https://github.com/BinWang28/RSE